ClawHub
Back to skill

Security audit

Guaikei Kuaishou Open Data Fetcher

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Kuaishou public-data fetcher, but users should know it sends queries to a third-party API and saves successful results locally.

Install only if you are comfortable using the guaikei.com API with a GUAIKEI_API_TOKEN. Treat saved files under logs/ as collected social-media data: review, protect, and delete them when no longer needed, especially on shared or corporate machines.

A.I.G

By Tencent
Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
82% confidence
Finding
The CLI persists fetched results to a local JSON file automatically after execution, which can leave potentially sensitive scraped data on disk without explicit user awareness or retention controls. In shared systems or agent environments, this increases the risk of unintended disclosure through world-readable files, backups, workspace collection, or later process access.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README states that all task results are automatically saved under `logs/`, but it does not clearly warn users that scraped public-data outputs may be persisted locally. This can expose collected profile, comment, or monitoring data to other local users, backups, or later unintended sharing, especially on shared machines or corporate endpoints.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The program writes the fetched results to disk without any explicit warning, confirmation, or dedicated save option in this file. Silent persistence is dangerous because users may believe the data only appears on stdout, while a durable local copy remains available to other users, tooling, or later compromise.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The CLI writes the full search output to a local JSON file whose filename includes the user-supplied keyword, and this file may contain sensitive search terms or result data. Because the file is created automatically without an explicit user consent flow or clear warning in normal execution, users may unknowingly leave sensitive artifacts on disk that can later be accessed by other local users, backup systems, or log collectors.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:15